Upload folder using huggingface_hub (#2)

- 866025f60df17d17f746331aaa15d175c40b47de2bc4e4b4a9d7ef9bf8b1877b (942d24f69f0cfd4273b10d9f6fc3983bbc7fe5be)
- 32ba96e2f1a3f4c64db2e34cc6e649d70ffce496b8dca2d005584e07de6ee917 (a5f500b14703117c04278b23158c7184f6d3253a)
- 2ad50f8fa208adfa5ae45d336dc3120149e3858d670769e1f3b9990a5daba5eb (b2192d5708e333335b9bb9d39816ab13e260cca0)
- 56365146cf445bf0a574b7327537e205f9337654ce4430ddbbe34775849663ab (d95cf220e2dc5621de4336dea3a249a286e8fb41)
- 127084866d44ffdc9924e40d3627fffb295c9b31b9a77048ecb158a4ce1522de (298788842bd40154bc2620f6b768beab6b9534ea)
- 2a63a9f1e20bae50f59ea8d95c8c9d899a1d4c0f78ea1175a5527107d8058802 (1f4b84fd5c8fc2f2d01567b7602af0ed9d9b26b8)
- 226d7f1e68f559f1b867f305b212c04e415c4d049686cbeb3f407788c5ef2d0c (6f9146d634963e0eb50a109b8c5f7b6d8bef6ef2)

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "/scratch1/jayr/gpt13b_itv3.5",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2Model"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "large_bs_inference": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 8192,
+  "n_embd": 5120,
+  "n_head": 40,
+  "n_inner": null,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "return_dict": false,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 50260
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfa526df470ca695e792a56cdbd89c41c023768661a763fea6a593ca59277f1
+size 9637826281

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39b4b18ae8677a75bcf76fef72ad3302a65d83bddbb2a7875dcb052d2d01c30
+size 9699205981

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc656acbae27131d84153e8daada6a446d0716728d1a1c2ad083e0bc0156d738
+size 9766295653

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f38d0df96c2f08a1f31c5bbe31adde0029e9e71519097dd39340204c8140e6a
+size 9699248065

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb7ce956c0c1480fbe92c1e43199ca5d2586d5813c030e837c031b22e3e2537
+size 9699206045

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7ca6af6180c9923d18c69eb68353948455d7546bb5419eaf30d3b1aba1dbe5
+size 5722174405

pytorch_model.bin.index.json

@@ -0,0 +1,571 @@
+{
+  "metadata": {
+    "total_size": 54223790240
+  },
+  "weight_map": {
+    "h.0.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.10.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.10.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.11.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.13.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.13.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.14.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.15.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.16.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.17.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.18.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.19.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.2.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.20.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.attn.c_attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.attn.c_attn.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.attn.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.attn.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.ln_2.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.ln_2.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.c_fc.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.c_fc.weight": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.c_proj.bias": "pytorch_model-00003-of-00006.bin",
+    "h.20.mlp.c_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "h.21.attn.bias": "pytorch_model-00003-of-00006.bin",
+    "h.21.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.attn.masked_bias": "pytorch_model-00003-of-00006.bin",
+    "h.21.ln_1.bias": "pytorch_model-00003-of-00006.bin",
+    "h.21.ln_1.weight": "pytorch_model-00003-of-00006.bin",
+    "h.21.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "h.21.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.21.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.22.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.23.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.24.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.25.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.26.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.c_fc.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.c_fc.weight": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.27.mlp.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.attn.c_attn.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.attn.c_attn.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.attn.c_proj.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.attn.c_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.attn.masked_bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.ln_1.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.ln_1.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.ln_2.bias": "pytorch_model-00004-of-00006.bin",
+    "h.28.ln_2.weight": "pytorch_model-00004-of-00006.bin",
+    "h.28.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.28.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.28.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.28.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.29.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.29.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.3.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.30.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.30.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.31.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.32.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.33.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.34.mlp.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.attn.c_attn.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.attn.c_attn.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.attn.c_proj.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.attn.c_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.attn.masked_bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.ln_1.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.ln_1.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.ln_2.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.ln_2.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.mlp.c_fc.bias": "pytorch_model-00005-of-00006.bin",
+    "h.35.mlp.c_fc.weight": "pytorch_model-00005-of-00006.bin",
+    "h.35.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.35.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.36.attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "h.36.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.36.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.ln_1.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.ln_1.weight": "pytorch_model-00006-of-00006.bin",
+    "h.36.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "h.36.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "h.36.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.36.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.ln_1.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.ln_1.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.37.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.ln_1.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.ln_1.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.38.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.attn.c_attn.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.attn.c_attn.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.attn.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.attn.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.attn.masked_bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.ln_1.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.ln_1.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.ln_2.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.ln_2.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.c_fc.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.c_fc.weight": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.c_proj.bias": "pytorch_model-00006-of-00006.bin",
+    "h.39.mlp.c_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "h.4.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00006.bin",
+    "h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.6.attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.6.attn.c_attn.bias": "pytorch_model-00001-of-00006.bin",
+    "h.6.attn.c_attn.weight": "pytorch_model-00001-of-00006.bin",
+    "h.6.attn.c_proj.bias": "pytorch_model-00001-of-00006.bin",
+    "h.6.attn.c_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "h.6.attn.masked_bias": "pytorch_model-00001-of-00006.bin",
+    "h.6.ln_1.bias": "pytorch_model-00001-of-00006.bin",
+    "h.6.ln_1.weight": "pytorch_model-00001-of-00006.bin",
+    "h.6.ln_2.bias": "pytorch_model-00001-of-00006.bin",
+    "h.6.ln_2.weight": "pytorch_model-00001-of-00006.bin",
+    "h.6.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.6.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.6.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.7.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.8.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.attn.c_attn.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.attn.c_attn.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.attn.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.attn.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.attn.masked_bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.ln_1.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.ln_1.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.ln_2.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.ln_2.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.c_fc.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.c_fc.weight": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.c_proj.bias": "pytorch_model-00002-of-00006.bin",
+    "h.9.mlp.c_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "ln_f.bias": "pytorch_model-00006-of-00006.bin",
+    "ln_f.weight": "pytorch_model-00006-of-00006.bin",
+    "wpe.weight": "pytorch_model-00001-of-00006.bin",
+    "wte.weight": "pytorch_model-00001-of-00006.bin"
+  }
+}